hdrboolean
Generate an HDR-encoded MP4. Requires HDR access on the account and a resolution of 720p or 1080p; not supported with loop.
Default: false
luma/ray/3.2/image-to-videoAgent Ray 3.2 by Luma - animate still images into dynamic videos with AI. Transform photos into cinematic clips with natural motion, camera movement, and optional audio generation.
Try the model
PNG, JPEG, WebP, or GIF · 20 MiB maximum
Customize your input with more control.
PNG, JPEG, WebP, or GIF · 20 MiB maximum
PNG, JPEG, WebP, or GIF · 20 MiB maximum
Your output will appear here
Complete the inputs, then click Run.
Luma Ray 3.2 image-to-video: animate a first frame (optionally toward an end frame or keyframes) into a 5 or 10 second clip, with optional HDR.
| Field | Type | Default | Notes |
|---|---|---|---|
prompt | string, required | — | Up to 6,000 characters. |
image | image URL, required | — | First frame. JPEG, PNG, or WebP URL. |
end_image | image URL | — | Optional last frame. |
resolution | 540p / 720p / 1080p | 720p | Sets the per-second rate. |
duration | 5 / 10 | 5 | Output length in seconds. |
loop | boolean | false | Make the clip loop. |
keyframes | string[] | — | Optional keyframe images. |
keyframe_indexes | integer[] | — | Frame positions for keyframes. |
exr_export | boolean | false | Also export EXR frames with HDR; triples the price. |
hdr | boolean | false | 16-bit HDR output (720p and 1080p); doubles the price. |
aspect_ratio | 21:9 / 16:9 / 4:3 / 1:1 / 3:4 / 9:16 | 16:9 | Output frame shape. |
$0.50 per 5-second clip at 540p, $1.00 at 720p, $2.00 at 1080p; 10 seconds costs double. HDR doubles and HDR with EXR export triples the 720p/1080p price.
| Output | 540p | 720p | 1080p |
|---|---|---|---|
| 5s (default) | $0.50 | $1.00 | $2.00 |
| 10s | $1.00 | $2.00 | $4.00 |
| 5s HDR | $0.50 | $2.00 | $4.00 |
Failed runs are not charged.
Related: luma/ray/3.2/text-to-video.
Start building
Submit this model through the SandBase Unified Run API.
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
-X POST "https://api.sandbase.ai/v1/run" \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'SANDBASE_JSON'
{
"model": "luma/ray/3.2/image-to-video",
"hdr": false,
"loop": false,
"image": "https://storage.googleapis.com/falserverless/gallery/example_inputs_liuyifei.png",
"prompt": "Low-angle shot of a majestic tiger prowling through a snowy landscape, leaving paw prints on the white blanket.",
"duration": 5,
"exr_export": false,
"resolution": "720p",
"aspect_ratio": "16:9"
}
SANDBASE_JSON
)
run_id=$(printf '%s' "$result" | jq -r .id)
for attempt in $(seq 1 120); do
status=$(printf '%s' "$result" | jq -r .status)
case "$status" in completed|failed|timeout) break ;; esac
sleep 2
result=$(curl --fail-with-body --silent \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
"https://api.sandbase.ai/v1/run/$run_id")
done
status=$(printf '%s' "$result" | jq -r .status)
[ "$status" = completed ] || { echo "Generation ended: $status" >&2; exit 1; }
printf '%s\n' "$result"Create a SandBase API key and set it in your server environment. All requests use Bearer authentication.
export SANDBASE_API_KEY="YOUR_API_KEY"Keep the key on your server. Do not expose it in browser code or commit it to a repository.
POST to /v1/run with this model ID and its inputs. The request example above includes submission and polling.
Use the returned run ID to poll until the status is completed, failed or timeout. Read output only after completed.
curl "https://api.sandbase.ai/v1/run/$RUN_ID" \
-H "Authorization: Bearer $SANDBASE_API_KEY"Pass a publicly accessible file URL in the model’s image, video or audio field. Supported formats and limits are shown beside each Playground input.
Use the upload or replace control on supported image fields in the Playground. Video URL fields accept a hosted driving video; they do not imply video-upload support.
hdrbooleanGenerate an HDR-encoded MP4. Requires HDR access on the account and a resolution of 720p or 1080p; not supported with loop.
Default: false
loopbooleanGenerate a seamless loop. Only valid for standard-dynamic-range generations without an end frame or keyframes.
Default: false
imagestringrequiredURL of the image used as the first frame of the video. Provide either image_url (optionally with end_image_url) or keyframes — the two anchoring modes are mutually exclusive.
promptstringrequiredText prompt describing the motion/scene to generate.
durationintegerDuration of the generated video. 10s requires multi-keyframe input (keyframes / keyframe_indexes); it is not supported with a single image_url / end_image_url anchor.
Default: 5
Possible values: 5, 10
end_imagestringOptional URL of an image used as the last frame. When set, the model interpolates between image_url and end_image_url. Cannot be combined with keyframes.
keyframesarrayMulti-keyframe image-to-video guide frames: 1-64 image URLs pinned at the positions given by keyframe_indexes. Mutually exclusive with image_url, end_image_url, and loop; unlocks 10s and HDR. Provide keyframes and keyframe_indexes together (same length).
exr_exportbooleanAlso export an EXR file alongside the MP4. Requires hdr=true and HDR access.
Default: false
resolutionstringResolution of the generated video. Higher resolutions cost more.
Default: "720p"
Possible values: "540p", "720p", "1080p"
aspect_ratiostringThe aspect ratio of the generated image.
Default: "16:9"
Possible values: "21:9", "16:9", "4:3", "1:1", "3:4", "9:16"
keyframe_indexesarrayOutput-frame positions (duration x 24fps: 5s -> 0-120, 10s -> 0-240) where each keyframes[i] is anchored. Non-negative, unique, and the same length as keyframes.
{
"model": "luma/ray/3.2/image-to-video",
"hdr": false,
"loop": false,
"image": "https://storage.googleapis.com/falserverless/gallery/example_inputs_liuyifei.png",
"prompt": "Low-angle shot of a majestic tiger prowling through a snowy landscape, leaving paw prints on the white blanket.",
"duration": 5,
"exr_export": false,
"resolution": "720p",
"aspect_ratio": "16:9"
}A completed run exposes its result in output. The following is the model’s saved example, not a new generation.
No example output has been published yet. Use Playground → Result → JSON after a completed run to inspect your response.